What is Hive?

Hive is an open source AI agent orchestration system. A fleet of specialized agents autonomously maintain GitHub repositories — triaging issues, writing fixes, opening PRs, and merging on green CI. A governor dynamically adjusts agent pace based on issue queue depth.

ACMM Framework

The AI-native Codebase Maturity Model (ACMM) defines 6 levels of AI agent autonomy, from advisory-only (L1) to fully autonomous (L6). Each level controls which agents are active and what actions they can take.

L1 — Idea

Advisory only. Agents analyze but don't act. Beads and heartbeat logs only.

L2 — Measured

Agents can open issues. No PRs. Quality gates begin.

L3 — CI/CD

Agents open hold-gated PRs. CI must pass. Human approval required.

L4 — Autonomous PR

Agents open and merge PRs on green CI. Hold labels for safety.

L5 — Self-Governing

Full autonomy with budget controls. Governor manages pace and cost.

L6 — Fully Autonomous

Multi-loop orchestration. Outreach, community engagement. Highest trust.

Agents

Supervisor — agent health monitoring, sweep analysis, stall detection
Scanner — triages issues, dispatches fixes, opens and merges PRs
Guide — documentation gaps, onboarding analysis, advisory reviews
CI-Maintainer — CI/CD health, workflow fixes, build monitoring
Quality — test coverage, integration tests, quality gates
Sec-Check — security scanning, PR security gate
Architect — cross-cutting RFCs, refactors, new features
Strategist — experiment design, A/B testing, strategy lab
Outreach — ADOPTERS outreach, community engagement
Brainstorm — on-demand ideation via Inception

Key Features

Governor — dynamic mode switching (idle/quiet/busy/surge) with per-agent cadences
Inception — interactive project scaffolding with llm-wiki and spec-kit
Knowledge Base — shared facts, wiki vaults, cross-agent priming
Audit Logging — all state changes logged with who/when/why
ACMM Proxy — per-agent HTTP proxy enforcing mode restrictions
Contributing — community agent contribution system